{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S4JN5KZ4KIUZTJWQZMSFAWB5WO","short_pith_number":"pith:S4JN5KZ4","schema_version":"1.0","canonical_sha256":"9712deab3c522999a6d0cb2450583db3858d5a769f2e0c3c2d83aadb477495ab","source":{"kind":"arxiv","id":"2511.21522","version":2},"attestation_state":"computed","paper":{"title":"Pessimistic Verification for Open Ended Math Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Li, Yang Liu, Yanxing Huang, Zejin Lin, Zihan Tang","submitted_at":"2025-11-26T15:52:52Z","abstract_excerpt":"Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-efficiency. Identifying that the primary bottleneck of verification lies in error detection capability, we propose pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw. We further introduce progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency. Ou"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.21522","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-26T15:52:52Z","cross_cats_sorted":[],"title_canon_sha256":"22535b5946fd58ccc11a3b0c398f0ebda2558f2a61f64c14219932c35ae34d4b","abstract_canon_sha256":"50269840a9a88281c7e8c22eabe6fb0580c90f8f432cf892e0a138ab979206d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:51.768185Z","signature_b64":"M1Sp5/CFNdWSEywgt33ooTP6Wf/UD9BD3edAyXfIBB5RJWGzR3lHRvjniaXRFHjH6p0JZy7E9AelSGHop6vOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9712deab3c522999a6d0cb2450583db3858d5a769f2e0c3c2d83aadb477495ab","last_reissued_at":"2026-06-23T03:13:51.767673Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:51.767673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pessimistic Verification for Open Ended Math Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peng Li, Yang Liu, Yanxing Huang, Zejin Lin, Zihan Tang","submitted_at":"2025-11-26T15:52:52Z","abstract_excerpt":"Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-efficiency. Identifying that the primary bottleneck of verification lies in error detection capability, we propose pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw. We further introduce progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.21522","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.21522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.21522","created_at":"2026-06-23T03:13:51.767735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.21522v2","created_at":"2026-06-23T03:13:51.767735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21522","created_at":"2026-06-23T03:13:51.767735+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4JN5KZ4KIUZ","created_at":"2026-06-23T03:13:51.767735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4JN5KZ4KIUZTJWQ","created_at":"2026-06-23T03:13:51.767735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4JN5KZ4","created_at":"2026-06-23T03:13:51.767735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.20531","citing_title":"Pseudo-Formalization for Automatic Proof Verification","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20531","citing_title":"Pseudo-Formalization for Automatic Proof Verification","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO","json":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO.json","graph_json":"https://pith.science/api/pith-number/S4JN5KZ4KIUZTJWQZMSFAWB5WO/graph.json","events_json":"https://pith.science/api/pith-number/S4JN5KZ4KIUZTJWQZMSFAWB5WO/events.json","paper":"https://pith.science/paper/S4JN5KZ4"},"agent_actions":{"view_html":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO","download_json":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO.json","view_paper":"https://pith.science/paper/S4JN5KZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.21522&json=true","fetch_graph":"https://pith.science/api/pith-number/S4JN5KZ4KIUZTJWQZMSFAWB5WO/graph.json","fetch_events":"https://pith.science/api/pith-number/S4JN5KZ4KIUZTJWQZMSFAWB5WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO/action/storage_attestation","attest_author":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO/action/author_attestation","sign_citation":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO/action/citation_signature","submit_replication":"https://pith.science/pith/S4JN5KZ4KIUZTJWQZMSFAWB5WO/action/replication_record"}},"created_at":"2026-06-23T03:13:51.767735+00:00","updated_at":"2026-06-23T03:13:51.767735+00:00"}